# davebcn87/pi-autoresearch

Autonomous experiment loop extension for pi

Repository: https://github.com/davebcn87/pi-autoresearch
Canonical: https://ross.abutalabs.com/products/pi-autoresearch
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-07-15T13:50:35+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 92, longevity 12
- inputs: {"age_days": 175, "days_push": 49, "days_rel": 55, "gap_med": 3.5, "n_releases_24m": 11}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7868, forks 448 (observed 2026-08-28T04:10:08.204649+00:00)

## What it is
A pi extension that runs autonomous optimization loops: try an idea, benchmark it, keep improvements, and revert regressions. Inspired by karpathy/autoresearch, it works for any measurable optimization target such as test speed, bundle size, or build times.

## Use cases
- automatically optimize unit test runtime
- reduce bundle size with an autonomous loop
- improve Lighthouse scores iteratively
- track and optimize LLM training loss
- speed up build times automatically
- benchmark commands and keep only improvements

## When to choose
- you use the pi coding agent and want hands-off optimization loops
- you have a measurable metric and a command to benchmark it
- you want automatic commits of wins and reverts of regressions

## When to avoid
- you don't use the pi coding agent
- your optimization target has no reliable automated measurement
- you need a standalone benchmarking tool outside an agent workflow

## Facets
- artifact type: plugin
- maturity: active
- function: benchmarking, agent-framework, developer-tools, cli, monitoring
- domain: developer-tools, performance, artificial-intelligence
- platform: cli, cross-platform
- tags: pi-extension, autonomous-experiment-loop, optimization, coding-agent, benchmark-loop, automation, nodejs

## Member repositories
- davebcn87/pi-autoresearch (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:08.204649+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:33:44.981993+00:00, confidence not recorded.
  - readme: https://github.com/davebcn87/pi-autoresearch (fetched 2026-08-28T04:10:08.204649+00:00, sha 8b76e47108ea)
  - registry_npm: https://registry.npmjs.org/pi-autoresearch (fetched 2026-08-29T08:30:28.388824+00:00, sha e631713b2abe)
- Data as of 2026-08-30T08:39:29.467469+00:00.